INDEX

Explanations

error messages and diagnostic codes

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AccessorTable

-0.73

AlterField

-0.55

 NgModule

-0.54

__*/

-0.54

 immu

-0.54

."));

-0.52

󠁢

-0.52

MOQ

-0.50

까지

-0.50

клопе

-0.49

POSITIVE LOGITS

0.61

 Codes

0.60

 code

0.57

 codes

0.56

 Nummer

0.56

int

0.52

 flag

0.52

 zero

0.52

 CODES

0.52

">—

0.51

Activations Density 0.938%

error messages and diagnostic codes

No Comments

No Known Activations